DSPP Project 3
Kristen Akey, kka2120
3/11/2021
library(tidyverse)
library(sf)
library(biscale)# load districts shapefile
districts <- read_sf("./raw-data/India_Districts_ADM2_GADM/India_Districts_ADM2_GADM.shp")# india-districts-census-2011.csv
india_census <- read_csv("./raw-data/india-districts-census-2011.csv")# summary statistics
india_census %>%
mutate(tot_pop = sum(Population),
lit_rate = mean((Male_Literate + Female_Literate)/ Population),
elec_household_rate = mean(Housholds_with_Electric_Lighting/Households),
water_household_rate =
mean(Location_of_drinking_water_source_Within_the_premises_Households/
Households),
internet_rate =
mean(Households_with_Internet/
Households),
rural_households = mean(Rural_Households/Households)
) %>%
select(tot_pop, lit_rate,elec_household_rate,water_household_rate, internet_rate,
rural_households) %>%
distinct() %>%
knitr::kable()| tot_pop | lit_rate | elec_household_rate | water_household_rate | internet_rate | rural_households |
|---|---|---|---|---|---|
| 1210854977 | 0.624632 | 0.476424 | 0.3035715 | 0.0166708 | 0.72615 |
districts <- districts %>%
rename(`District code` = FID) %>%
left_join(., india_census, on="District")
### Population
# Male_Literate
# Female_Literate
## Households
# Housholds_with_Electric_Lighting
# Households_with_Internet
# Households_with_Computer
# Rural_Households
# Urban_Households
# Below_Primary_Education
# Households_with_Television
# Households_with_separate_kitchen_Cooking_inside_house
# Not_having_bathing_facility_within_the_premises_Total_Households
# Location_of_drinking_water_source_Within_the_premises_Households
# Married_couples_3_or_more_Households
## Total_Education
# educ <- c("Below_Primary_Education", "Primary_Education", "Middle_Education", "Secondary_Education", "Higher_Education", "Graduate_Education", "Other_Education")
districts <- districts %>%
group_by(`District code`) %>%
mutate(prop_literate = (Male_Literate + Female_Literate)/Population,
prop_households_w_elec_lighting =
Housholds_with_Electric_Lighting / Households,
prop_households_rural = Rural_Households / Households,
prop_households_urban = Urban_Households / Households,
prop_below_primary_educ =
Below_Primary_Education / Total_Education,
prop_households_w_tv = Households_with_Television / Households,
prop_households_w_internet = Households_with_Internet / Households,
prop_bath_not_in_home = Not_having_bathing_facility_within_the_premises_Total_Households / Households,
prop_water_in_home = Location_of_drinking_water_source_Within_the_premises_Households / Households)districts$Population_quant <- with(districts,
cut(Population,
breaks = qu <- quantile(Population, probs = seq(0,1, by=0.2), na.rm=T),
labels = round(qu[-1],2), include.lowest=TRUE))
ggplot(data=districts) +
geom_sf(aes(fill=Population_quant),size=.03) +
theme_void() +
scale_fill_brewer(palette = "Reds", na.value = "grey80",
name="Population") +
ggtitle("Population, India 2011") +
theme(panel.grid.major = element_line("transparent"),
axis.text = element_blank(),
text=element_text(family="Noto Serif"),
plot.title = element_text(hjust = .5, vjust=-.6),
plot.background = element_rect(fill="white", color=NA)) +
ggsave("population.png", dpi=300)
rural/urban areas
districts$prop_households_rural_quant <- with(districts,
cut(prop_households_rural,
breaks = qu <- quantile(prop_households_rural, probs = seq(0,1, by=0.2), na.rm=T),
labels = paste0(round(qu[-1],2)*100, "%"), include.lowest=TRUE))
ggplot(data=districts) +
geom_sf(aes(fill=prop_households_rural_quant),size=.03) +
theme_void() +
scale_fill_brewer(palette = "Oranges", na.value = "grey80",
name="Percentage Rural") +
ggtitle("Rural Households by District, India 2011") +
theme(panel.grid.major = element_line("transparent"),
axis.text = element_blank(),
text=element_text(family="Noto Serif")) 
districts$prop_households_urban_quant <- with(districts,
cut(prop_households_urban,
breaks = qu <- quantile(prop_households_urban, probs = seq(0,1, by=0.2), na.rm=T),
labels = paste0(round(qu[-1],2)*100, "%"), include.lowest=TRUE))
ggplot(data=districts) +
geom_sf(aes(fill=prop_households_urban_quant),size=.03) +
theme_void() +
scale_fill_brewer(palette = "PuBuGn", na.value = "grey80",
name="Percentage Urban") +
ggtitle("Urban Households by District, India 2011") +
theme(panel.grid.major = element_line("transparent"),
axis.text = element_blank(),
text=element_text(family="Noto Serif")) 
# more ubran vs more rural
# difference between avacode vs mango production
districts <- districts %>%
mutate(diff_urban_rural = prop_households_urban - prop_households_rural)
ggplot() +
geom_sf(data=districts, aes(fill=diff_urban_rural), size=.1, color="grey10") +
scale_fill_gradient2(low = "#ffc324", mid = "grey99",
high = "#663399", midpoint = 0, space = "Lab",
limit = c(-1,1),
breaks = c(-1,-.5,0,.5,1),
labels = c("+100%\nrural", "+50%\nrural","Even",
"+50%\nurban", "+100%\nurban"),
name = "") +
theme_void() +
theme(legend.text = element_text(size=5.5),
legend.key.size = unit(.5, "cm"),
legend.direction="horizontal",
legend.position = c(.35,.009),
legend.justification = c(-1,-1.3),
plot.background = element_rect(fill="lightblue", color=NA),
text=element_text(family="Noto Serif")
) +
ggtitle("Urban/Rural Population Dispersion by District, 2011") +
ggsave("urban_rural.png",dpi=300)
districts$prop_literate_quant <- with(districts,
cut(prop_literate,
breaks = qu <- quantile(prop_literate, probs = seq(0,1, by=0.2), na.rm=T),
labels = paste0(round(qu[-1],2)*100, "%"), include.lowest=TRUE))
ggplot(data=districts) +
geom_sf(aes(fill=prop_literate_quant),size=.03) +
theme_void() +
scale_fill_brewer(palette = "RdPu", na.value = "grey80",
name="Percentage\nLiterate") +
ggtitle("Literacy Rate by District, India 2011") +
theme(panel.grid.major = element_line("transparent"),
axis.text = element_blank(),
legend.position = c(.6,.2),
plot.title = element_text(hjust = .5, vjust=-.6),
plot.background = element_rect(fill="white", color=NA),
text=element_text(family="Noto Serif")) +
ggsave("literacy.png", dpi=300)
districts$prop_households_w_internet_quant <- with(districts,
cut(prop_households_w_internet,
breaks = qu <- quantile(prop_households_w_internet, probs = seq(0,1, by=0.2), na.rm=T),
labels = paste0(round(qu[-1],2)*100, "%"), include.lowest=TRUE))
ggplot(data=districts) +
geom_sf(aes(fill=prop_households_w_internet_quant),size=.03) +
theme_void() +
scale_fill_brewer(palette = "Reds", na.value = "grey80",
name="Percentage with\nHousehold Internet") +
ggtitle("Households with Internet by District, India 2011") +
theme(panel.grid.major = element_line("transparent"),
axis.text = element_blank(),
text=element_text(family="Noto Serif")) 
root_api <- 'http://api.nightlights.io/months/2011.3-2011.3/states'
states <- jsonlite::fromJSON(root_api)
full_lights_df <- data.frame()
for (state_name in states$key) {
root_api <- paste0('http://api.nightlights.io/months/2011.3-2011.3/states/',
state_name,
'/districts')
light_data <- jsonlite::fromJSON(root_api)
full_lights_df <- rbind(full_lights_df,light_data)
}
# sepearte key for District name
pattern_2 <- "uttar-pradesh|west-bengal|himachal-pradesh|madhya-pradesh|andhra-pradesh"
pattern_3 <- "jammu-&-kashmir"
full_lights_df$`District name` <- "-"
full_lights_df$`State Name` <- "-"
for (i in 1:length(str_split(full_lights_df$key, pattern="-"))) {
words_split <- str_split(full_lights_df$key, pattern="-")[[i]]
if (grepl(pattern_2, x=full_lights_df[i,]$key)) {
full_lights_df[i,]$`District name` <- paste(words_split[3:length(words_split)],
collapse=" ")
full_lights_df[i,]$`State Name` <- paste(words_split[1:2],
collapse=" ")
}
else if (grepl(pattern_3, x=full_lights_df[i,]$key)) {
full_lights_df[i,]$`District name` <- paste(words_split[4:length(words_split)],
collapse=" ")
full_lights_df[i,]$`State Name` <- paste(words_split[1],"and",words_split[3],
collapse=" ")
}
else {
full_lights_df[i,]$`District name` <- paste(words_split[2:length(words_split)],
collapse=" ")
full_lights_df[i,]$`State Name` <- paste(words_split[1],
collapse=" ")
}
}full_lights_df <- full_lights_df %>%
mutate(`State Name` = toupper(`State Name`),
`District name` = str_to_title(`District name`))
full_lights_df[full_lights_df$`District name`=="Y.s.r",]$`District name` <- 'Y.S.R.'
full_lights_df[full_lights_df$`District name`=="Marigaon",]$`District name` <- 'Morigaon'
full_lights_df[full_lights_df$`District name`=="Sibsagar",]$`District name` <- 'Sivasagar'
full_lights_df[full_lights_df$`District name`=="Janjgir Champa",]$`District name` <- 'Janjgir - Champa'
full_lights_df[full_lights_df$`State Name`=="DELHI",]$`State Name` <- 'NCT OF DELHI'
full_lights_df[full_lights_df$`District name`=="Lahul & Spiti",]$`District name` <- 'Lahul AND Spiti'
full_lights_df[full_lights_df$`District name`=="Leh (Ladakh)",]$`District name` <- 'Leh(Ladakh)'
full_lights_df[full_lights_df$`District name`=="Pakaur",]$`District name` <- 'Pakur'
full_lights_df[full_lights_df$`District name`=="Saraikela Kharsawa",]$`District name` <- 'Saraikela-Kharsawan'
full_lights_df[full_lights_df$`District name`=="East Nimar",]$`District name` <- 'Khandwa (East Nimar)'
full_lights_df[full_lights_df$`District name`=="West Nimar",]$`District name` <- 'Khargone (West Nimar)'
full_lights_df[full_lights_df$`District name`=="Ri Bhoi",]$`District name` <- 'Ribhoi'
full_lights_df[full_lights_df$`District name`=="North District",]$`District name` <- 'North District'
full_lights_df[full_lights_df$`District name`=="Barabanki",]$`District name` <- 'Bara Banki'
full_lights_df[full_lights_df$`District name`=="Bulandshahar",]$`District name` <- 'Bulandshahr'
districts <- districts %>%
left_join(., full_lights_df, on=c(`State Name`,`District name`))
districts$vis_median <- as.double(districts$vis_median)vis_median – Average median of measurements for this month
districts$vis_median_quant <- with(districts,
cut(vis_median,
breaks = qu <- quantile(vis_median, probs = seq(0,1, by=0.2), na.rm=T),
labels = round(qu[-1],2), include.lowest=TRUE))
ggplot(data=districts) +
geom_sf(aes(fill=vis_median_quant), size=.04) +
theme_void() +
scale_fill_brewer(palette = "YlGnBu", na.value = "grey80",
name="Average Median\nof Light\nMeasurements") +
ggtitle("Lights by District, India March 2011") +
theme(panel.grid.major = element_line("transparent"),
axis.text = element_blank(),
plot.background = element_rect(fill="white", color=NA),
plot.title = element_text(hjust=.9,vjust=-4),
legend.position = c(.75,.2),
text=element_text(family="Noto Serif")) +
ggsave("median_lights.png", dpi=300)
districts$vis_median_break <- cut(districts$vis_median,
breaks = c(-1.5500, 0, 8,18, 28, 48,58.3971),
labels = c("0","8","18", "28", "48", "58"))
ggplot(data=districts) +
geom_sf(aes(fill=vis_median_break), size=.04) +
theme_void() +
scale_fill_brewer(palette = "YlGnBu", na.value = "grey80",
name="Average Median\nof Light\nMeasurements") +
ggtitle("Lights by District, India March 2011") +
theme(panel.grid.major = element_line("transparent"),
axis.text = element_blank(),
plot.background = element_rect(fill="white", color=NA),
plot.title = element_text(hjust=.9,vjust=-4),
legend.position = c(.75,.2),
text=element_text(family="Noto Serif")) +
ggsave("median_lights_breaks.png", dpi=300)
quantile(districts$vis_median, na.rm=T)## 0% 25% 50% 75% 100%
## -1.5500 -0.3768 0.2941 1.5843 58.3971# iterate through files and import and bind all csvs
library(data.table)
files <- list.files(path = "./raw-data/India_2011_census_tables/2011",
full.names = T, recursive = T, pattern = ".csv")
files <- files[str_sub(files, start= -3)=="csv"]
full_csv <- c()
for (f in files) {
filename <- str_sub(f, start= 46, end=-6)
filenamefull <- read_csv(f)
filenamefull <- filenamefull %>%
filter(Year=='2010-11') %>%
pivot_longer(cols=colnames(filenamefull)[3:length(colnames(filenamefull))])
if (nrow(filenamefull)==0) {
filenamefull <- read_csv(f)
filenamefull <- filenamefull %>%
filter(Year=='2009-10') %>%
pivot_longer(cols=colnames(filenamefull)[3:length(colnames(filenamefull))])
}
filenamefull$`State Name` <- filename
full_csv <- rbind(full_csv, filenamefull)
}
# add space between lowercase and uppercase
full_csv$`State Name` <- gsub("([a-z])([A-Z])", "\\1 \\2", full_csv$`State Name`)
full_csv$`State Name` <- toupper(full_csv$`State Name`)
full_csv[full_csv$`State Name`=="ODISHA",]$`State Name` <- 'ORISSA'
full_csv <- full_csv %>%
rename(`District name`=name)
# fix district name differences for join
full_csv[full_csv$`District name`=="Godavari East",]$`District name` <- 'East Godavari'
full_csv[full_csv$`District name`=="Mahabubnagar",]$`District name` <- 'Mahbubnagar'
full_csv[full_csv$`District name`=="Visakapatnam",]$`District name` <- 'Visakhapatnam'
full_csv[full_csv$`District name`=="Kamrup (Metropolitan)",]$`District name` <- 'Kamrup Metropolitan'
full_csv[full_csv$`District name`=='Kamrup Rural',]$`District name` <- 'Kamrup'
full_csv[full_csv$`District name`=="Samstipur",]$`District name` <- 'Samastipur Metropolitan'
full_csv[full_csv$`District name`=="Bangalore Urban",]$`District name` <- 'Bangalore'
full_csv[full_csv$`District name`=="Chickballapur",]$`District name` <- 'Chikkaballapura'
full_csv[full_csv$`District name`=="Chickmagalur",]$`District name` <- 'Chikmagalur'
full_csv[full_csv$`District name`=="Davangere",]$`District name` <- 'Davanagere'
full_csv[full_csv$`District name`=="Ramnagara",]$`District name` <- 'Ramanagara'
full_csv[full_csv$`District name`=="Yadagiri",]$`District name` <- 'Yadgir'
full_csv[full_csv$`District name`=="Kasargode",]$`District name` <- 'Kasaragod'
full_csv[full_csv$`District name`=="Ahmednagar",]$`District name` <- 'Ahmadnagar'
full_csv[full_csv$`District name`=="Gondia",]$`District name` <- 'Gondiya'
full_csv[full_csv$`District name`=="Wahim",]$`District name` <- 'Washim'
full_csv[full_csv$`District name`=="Yavatnal",]$`District name` <- 'Yavatmal'
full_csv[full_csv$`District name`=="Angul",]$`District name` <- 'Anugul'
full_csv[full_csv$`District name`=="Deogarh",]$`District name` <- 'Debagarh'
full_csv[full_csv$`District name`=="Jagatsinghpur",]$`District name` <- 'Jagatsinghapur'
full_csv[full_csv$`District name`=="Jajpur",]$`District name` <- 'Jajapur'
full_csv[full_csv$`District name`=="Taran Tarn",]$`District name` <- 'Tarn Taran'
full_csv[full_csv$`District name`=="Auraiyya",]$`District name` <- 'Auraiya'
full_csv[full_csv$`District name`=="Bagpat",]$`District name` <- 'Baghpat'
full_csv[full_csv$`District name`=="Barabanki",]$`District name` <- 'Bara Banki'
full_csv[full_csv$`District name`=="BulandShahar",]$`District name` <- 'Bulandshahr'
full_csv[full_csv$`District name`=="Etawa",]$`District name` <- 'Etawah'
full_csv[full_csv$`District name`=="Kanpur Dehat",]$`District name` <- 'Kanpur: Rural'
full_csv[full_csv$`District name`=="Gautambudh Nagar",]$`District name` <- 'Gautam Buddha Nagar'
full_csv[full_csv$`District name`=="Kanpur Nagar",]$`District name` <- 'Kanpur: Urban'
full_csv[full_csv$`District name`=="Maharajganj",]$`District name` <- 'Mahrajganj'
full_csv[full_csv$`District name`=="Sant Kabeer Nagar",]$`District name` <- 'Sant Kabir Nagar'
full_csv[full_csv$`District name`=="Sant Ravidas Nagar",]$`District name` <- 'Sant Ravidas Nagar (Bhadohi)'
full_csv[full_csv$`District name`=="Shravasti",]$`District name` <- 'Shrawasti'
full_csv[full_csv$`District name`=="Siddharth Nagar",]$`District name` <- 'Siddharthnagar'
full_csv[full_csv$`District name`=="24-Parganas (North)",]$`District name` <- 'North Twenty Four Parganas'
full_csv[full_csv$`District name`=="24-Parganas (South)",]$`District name` <- 'South Twenty Four Parganas'
full_csv[full_csv$`District name`=="Burdwan",]$`District name` <- 'Barddhaman'
full_csv[full_csv$`District name`=="Cooch Behar",]$`District name` <- 'Koch Bihar'
full_csv[full_csv$`District name`=="Darjeeling",]$`District name` <- 'Darjiling'
full_csv[full_csv$`District name`=="Howrah",]$`District name` <- 'Haora'
full_csv[full_csv$`District name`=="Hooghly",]$`District name` <- 'Hugli'
full_csv[full_csv$`District name`=="Malda",]$`District name` <- 'Maldah'
full_csv[full_csv$`District name`=="Midnapore West",]$`District name` <- 'Paschim Medinipur'
full_csv[full_csv$`District name`=="Midnapore East",]$`District name` <- 'Purba Medinipur'
full_csv[full_csv$`District name`=="Purulia",]$`District name` <- 'Puruliya'
full_csv[full_csv$`District name`=="Godavari West",]$`District name` <- 'West Godavari'
gdp_csv <- full_csv %>%
filter(Description=='GDP (in Rs. Cr.)') %>%
rename(GDP = value) %>%
select(!Description)
growth_csv <- full_csv %>%
filter(Description=='Growth Rate % (YoY)') %>%
rename(growth_rate = value) %>%
select(!Description)districts_gdp <- districts %>%
inner_join(., gdp_csv, on=c('State Name','District name'))
districts_growth <- districts %>%
inner_join(., growth_csv, on=c('State Name','District name'))districts_gdp$GDP_quant <- with(districts_gdp,
cut(GDP,
breaks = qu <- quantile(GDP, probs = seq(0,1, by=0.2), na.rm=T),
labels = round(qu[-1]), include.lowest=TRUE))
ggplot() +
geom_sf(data=districts, size=.05) +
geom_sf(data=districts_gdp, aes(fill=GDP_quant), size=.05) +
theme_void() +
ggtitle("GDP 2011") +
theme(panel.grid.major = element_line("transparent"),
axis.text = element_blank(),
plot.background = element_rect(fill="white", color=NA),
plot.title = element_text(hjust=.9,vjust=-4),
legend.position = c(.75,.2),
text=element_text(family="Noto Serif")) +
scale_fill_brewer(palette = "Greens", na.value = "grey80", name="GDP") +
ggsave("gdp.png", dpi=300)
Bivariate map of lights and GDP
# create classes
data <- bi_class(districts_gdp,x = vis_median, y = GDP, style = "quantile", dim = 3)
map <- ggplot() +
geom_sf(data=districts, color="grey20", fill="white",size=.1) +
geom_sf(data = data %>%
filter(!is.na(vis_median)),
aes(fill = bi_class),
color = "grey20", size = 0.1, show.legend = FALSE) +
bi_scale_fill(pal = "DkCyan", dim = 3) +
ggtitle("GDP and Lights, India 2011") +
theme_void() +
theme(text=element_text(family="Noto Serif"),
plot.title = element_text(size=12, hjust=.6, vjust=-24),
plot.background = element_rect(fill="grey65", color=NA),
panel.background = element_rect(fill="grey65", color=NA),
panel.grid.major = element_line("transparent"),
axis.text = element_blank())
legend <- bi_legend(pal = "DkCyan",
dim = 3,
xlab = "More Lights ",
ylab = "Higher GDP ",
size = 8.3) +
theme(plot.background = element_rect(fill="grey65", color=NA),
panel.background = element_rect(fill="grey65", color=NA),
panel.grid.major=element_blank(),
panel.grid.minor=element_blank())
library(cowplot)
finalPlot <- ggdraw() +
draw_plot(map, 0, 0, 1, 1) +
draw_plot(legend, 0.6, .15, 0.2, 0.2) +
ggsave("bi_gdp_lights.png",dpi=300)OLS regression
districts_gdp_log <- districts_gdp %>%
mutate(GDP_stand = (GDP/Population)*1000,
log_GDP = log(GDP))
# correlation between log GDP and lots
summary(lm(vis_median ~ log_GDP, data = districts_gdp_log))##
## Call:
## lm(formula = vis_median ~ log_GDP, data = districts_gdp_log)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.8284 -1.3288 -0.6661 0.6017 20.7524
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -5.06982 0.83750 -6.054 4.80e-09 ***
## log_GDP 0.76604 0.09954 7.696 2.75e-13 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.347 on 266 degrees of freedom
## (3 observations deleted due to missingness)
## Multiple R-squared: 0.1821, Adjusted R-squared: 0.179
## F-statistic: 59.23 on 1 and 266 DF, p-value: 2.752e-13summary(lm(log_GDP ~ vis_median, data = districts_gdp_log))##
## Call:
## lm(formula = log_GDP ~ vis_median, data = districts_gdp_log)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.6332 -0.4031 0.2441 0.8383 2.9201
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 7.98540 0.08914 89.581 < 2e-16 ***
## vis_median 0.23774 0.03089 7.696 2.75e-13 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.308 on 266 degrees of freedom
## (3 observations deleted due to missingness)
## Multiple R-squared: 0.1821, Adjusted R-squared: 0.179
## F-statistic: 59.23 on 1 and 266 DF, p-value: 2.752e-13# additional covariates
m1 <- lm(log_GDP ~ vis_median+prop_households_rural + prop_literate + prop_households_w_elec_lighting + prop_bath_not_in_home, data = districts_gdp_log)
summary(m1)##
## Call:
## lm(formula = log_GDP ~ vis_median + prop_households_rural + prop_literate +
## prop_households_w_elec_lighting + prop_bath_not_in_home,
## data = districts_gdp_log)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.3457 -0.5325 0.0800 0.7199 1.9675
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.581722 0.778937 8.450 2.05e-15 ***
## vis_median -0.007452 0.031792 -0.234 0.814871
## prop_households_rural -2.040751 0.567250 -3.598 0.000384 ***
## prop_literate 3.051977 0.804400 3.794 0.000184 ***
## prop_households_w_elec_lighting 2.962364 0.438540 6.755 9.19e-11 ***
## prop_bath_not_in_home 0.571033 0.464634 1.229 0.220176
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.018 on 262 degrees of freedom
## (3 observations deleted due to missingness)
## Multiple R-squared: 0.512, Adjusted R-squared: 0.5027
## F-statistic: 54.97 on 5 and 262 DF, p-value: < 2.2e-16m1 <- lm(vis_median ~ log_GDP+prop_households_rural + prop_literate + prop_households_w_elec_lighting + prop_bath_not_in_home, data = districts_gdp_log)
summary(m1)##
## Call:
## lm(formula = vis_median ~ log_GDP + prop_households_rural + prop_literate +
## prop_households_w_elec_lighting + prop_bath_not_in_home,
## data = districts_gdp_log)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.9815 -0.9263 -0.1610 0.6347 17.6412
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.27777 1.66267 3.776 0.000197 ***
## log_GDP -0.02813 0.12003 -0.234 0.814871
## prop_households_rural -6.65679 1.05152 -6.331 1.05e-09 ***
## prop_literate -1.18635 1.60366 -0.740 0.460099
## prop_households_w_elec_lighting 3.29289 0.90063 3.656 0.000309 ***
## prop_bath_not_in_home -0.82441 0.90396 -0.912 0.362607
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.978 on 262 degrees of freedom
## (3 observations deleted due to missingness)
## Multiple R-squared: 0.4282, Adjusted R-squared: 0.4173
## F-statistic: 39.24 on 5 and 262 DF, p-value: < 2.2e-16